• Journal of Korea Multimedia Society
• /
• v.22 no.12
• /
• pp.1457-1465
• /
• 2019

3D convolution is to stack multiple consecutive frames to form a cube, and then apply the 3D convolution kernel in the cube. In this structure, each feature map of the convolutional layer is connected to multiple adjacent sequential frames in the previous layer, thus capturing the motion information. However, due to the changes of pedestrian posture, motion and position, the convolution at the same place is inappropriate, and when the 3D convolution kernel is convoluted in the time domain, only time domain features of three consecutive frames can be extracted, which is not a good enough to get action information. This paper proposes an action recognition method based on feature fusion of 3D convolutional neural network. Based on the VGG16 network model, sending a pre-acquired optical flow image for learning, then get the time domain features, and then the feature of the time domain is extracted from the features extracted by the 3D convolutional neural network. Finally, the behavior classification is done by the SVM classifier.

• International journal of advanced smart convergence
• /
• v.4 no.2
• /
• pp.20-28
• /
• 2015

In this paper, we propose an effective tracking algorithm with an appearance model based on features extracted from a video frame with posture variation and camera view point adaptation by employing the non-adaptive random projections that preserve the structure of the image feature space of objects. The existing online tracking algorithms update models with features from recent video frames and the numerous issues remain to be addressed despite on the improvement in tracking. The data-dependent adaptive appearance models often encounter the drift problems because the online algorithms does not get the required amount of data for online learning. So, we propose an effective tracking algorithm with an appearance model based on features extracted from a video frame.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1743-1746
• /
• 2003

C. elegans often used to study of function of gene, but it is difficult for human observation to distinguish the mutants of C. elegans. To solve this problem, the system, which can be classified automatically using the computer vision, is studying now. In the previous works , they described the auto-tracking system and the egg-laying timing modeling, which are used to automated-classily system. In this paper, we use three kinds of features, which are related to movement , size and posture of the worm, and each feature is described mathematically and normalized. In experimental result, we validated the features for the hierarchical clustering, And we used the Calinski and Harabasz's method to find the appropriate cluster number.

• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• pp.1-7
• /
• 2019

Recently, smart factories have attracted much attention as a result of the 4th Industrial Revolution. Existing factory automation technologies are generally designed for simple repetition without using vision sensors. Even small object assemblies are still dependent on manual work. To satisfy the needs for replacing the existing system with new technology such as bin picking and visual servoing, precision and real-time application should be core. Therefore in our work we focused on the core elements by using deep learning algorithm to detect and classify the target object for real-time and analyzing the object features. We chose YOLO CNN which is capable of real-time working and combining the two tasks as mentioned above though there are lots of good deep learning algorithms such as Mask R-CNN and Fast R-CNN. Then through the line and inside features extracted from target object, we can obtain final outline and estimate object posture.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.15 no.2
• /
• pp.114-123
• /
• 2005

We analyzed the demographic and job features of 197 shipyard workers with work-related musculoskeletal disorders(WMSDs) compensated by the Industrial Accident Compensation Insurance Act, and the features of the disorders, the causes of operation and the induced behaviors. The three shipbuilding companies surveyed were located in Busan Metropolitan city and Gyungsangnam-do. The results were as follows. 1. The ages of WMSDs patients in shipyard were $43.6{\pm}8.6$ and the job tenure was $14.3{\pm}5.6$. The 40's of them was 40.1%, and the 30's was 29.4%. Patients less than 5 year-work duration were 85.3%, and ones more than 16 year-work duration 6.6%. In occupations, welders were 32.5%, pre-welders 17.3%, and setting engineers 6.6%. 2. The causes of WMSDs in shipyard were works(95.4%) and outer crash or accident shock (3.6%). Based on the standard of the NIOSH induced behaviors, the causes were awkward posture (62.9%), excessive movement(19.3%) and repetitive movement(13.7%). 3. The compensated WMSDs by body part was the highest, 36%, in the spines, 32.0% in both the upper limbs and the spines, and 14% in the upper limbs. The number of cases of WMSDs in body were 96 in the cervical, 79 in the lumbar and 72 in the shoulders. 4. As a result of chi-square test(${\chi}^2$) between diagnosis and operation in body, welding and spot welding had the most diagnoses in all parts of the body among other occupations. Chi-square test(${\chi}^2$) between diagnosis and induced behavior in body showed that awkward postures recorded the highest rate and repetitive movements was the second. 5. The most hazardous occupation was the welding(incidence rate=9.7) and the most hazardous behavior was the awkward posture.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.04a
• /
• pp.141-146
• /
• 1996

Hand posture and force, which define aspects of the way an object is grasped, are features of robotics manipulation. A means for specifying these grasping "flavors" has been developed that uses an instrumented glove equipped with joint and force sensors. The new grasp specification system is being used at the Pennsylvania State University (Penn State) in a Virtual Reality based Point-and-Direct(VR-PAD) robotics implementation. In the Computer Integrated Manufacturing (CIM) Laboratory at Penn State, hand posture and force data were collected for manipulating bricks and other items that require varying amounts of force at multiple pressure points. The feasibility of measuring desired grasp characteristics was demonstrated for a modified Cyberglove impregnated with FSR (Force Sensitive Resistor) pressure sensors in the fingertips. A joint/force model relating the parameters of finger articulation and pressure to various lifting tasks was validated for the instrumented "wired" glove. Operators using such a modified glove may ultimately be able to configure robot grasping tasks in environments involving hazardous waste remediation, flexible manufacturing, space operations and other flexible robotics applications. In each case, the VR-PAD approach improved the computational and delay problems of real-time multiple-degree-of-freedom force feedback telemanipulation.ck telemanipulation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.703-706
• /
• 2007

The real-time monitoring about the activity of the human provides useful information about the activity quantity and an ability. This study developed a system for human physical activity assessment in ambulatory monitoring using portable sensing device combining a tri-axial accelerometer and wireless sensor node. This real-time system is able to identify several postures, posture transitions and movements with classification algorithm. In addition, this system also features fall detection capability. The results of the assessment for evaluating the performance of the system show high identification accuracy.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.3
• /
• pp.153-160
• /
• 2008

One of the most important features of the Mobile Manipulator is redundant freedom. Using it's redundant freedom, a Mobile Manipulator can move in various modes, and perform dexterous motions. In this paper, to improve robot job performance, two robots -mobile robot, task robot- are joined together to perform a job, we studied the optimal position and posture of a Mobile Manipulator to achieve a minimum of movement of each robot joint. Kinematics of mobile robot and task robot is solved. Using the mobility of a Mobile robot, the weight vector of robots is determined. Using the Gradient method, global motion trajectory is minimized, so the job which the Mobile Manipulator performs is optimized. The proposed algorithm is verified with PURL-II which is Mobile Manipulator combined Mobile robot and task robot, and the results are discussed.

• Journal of the Ergonomics Society of Korea
• /
• v.15 no.2
• /
• pp.165-176
• /
• 1996

Hand posture and force, which define aspects of the way an object is grasped, are features of robotic manipulation. A means for specifying these grasping "flavors" has been developed that uses an instrumented glove equipped with joint and force sensors. The new grasp specification system is being used at the Pennsylvania State University (Penn State) in a Virtual Reality based Point-and-Direct (VR-PAD) robotics implementation. In the Computer Integrated Manufacturing (CIM) Laboratory at Penn State, hand posture and force data were collected for manipulating bricks and other items that require varying amounts of force at multiple pressure points. The feasibility of measuring desired grasp characteristics was demonstrated for a modified Cyberglove impregnated with FSR (Force Sensitive Resistor) pressure sensors in the fingertips. A joint/force model relating the parameters of finger articulation and pressure to various lifting tasks was validated for the instrumented "wired" glove. Operators using such a modified glove may ultimately be able to configure robot grasping tasks in environments involving hazardous waste remediation, flexible manufactruing, space operations and other flexible robotics applications. In each case, the VR-PAD approach improved the computational and delay problems of real-time multiple- degree-of-freedom force feedback telemanipulation.

• Journal of Auto-vehicle Safety Association
• /
• v.16 no.1
• /
• pp.55-61
• /
• 2024

The advancement of autonomous driving technology is expected to transform cars beyond mere transportation into multifunctional spaces for relaxation and entertainment. As autonomous driving technology becomes more sophisticated, with no need for direct driver control, the interior space of vehicles is anticipated to be utilized for various purposes. Consequently, the importance of car seats, the component most frequently interacted with by passengers during travel, is expected to significantly rise. However, existing car seats are designed according to a seated posture, necessitating verification for passenger safety and seat structure considerations in the context of autonomous driving, where comfortable postures may differ. For these reasons, it is anticipated that the seats of future autonomous vehicles will evolve with the incorporation of additional safety and convenience features. In this study, a three-axis car simulator was employed to investigate seat angles for comfortable postures of passengers in autonomous driving scenarios. Representative postures were identified to enhance passenger convenience. Furthermore, functional design factors contributing to passenger comfort were applied to conduct seat design, seat structure, and collision analysis, with an analysis of the interrelationships among design factors.